Papers › InstructPix2Pix: Learning to Follow Image Editing Instructions

InstructPix2Pix: Learning to Follow Image Editing Instructions

17 Nov 2022CVPR 2023 1arXiv:2211.09800archive 2025-07-28

Tim Brooks, Aleksander Holynski, Alexei A. Efros

We propose a method for editing images from human instructions: given an input image and a written instruction that tells the model what to do, our model follows these instructions to edit the image. To obtain training data for this problem, we combine the knowledge of two large pretrained models -- a language model (GPT-3) and a text-to-image model (Stable Diffusion) -- to generate a large dataset of image editing examples. Our conditional diffusion model, InstructPix2Pix, is trained on our generated data, and generalizes to real images and user-written instructions at inference time. Since it performs edits in the forward pass and does not require per example fine-tuning or inversion, our model edits images quickly, in a matter of seconds. We show compelling editing results for a diverse collection of input images and written instructions.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (timothybrooks/instruct-pix2pix) is linked to this paper; the 20 samples below come from 4 community repositories. Syntology harvested code from timothybrooks/instruct-pix2pix for another paper.

timothybrooks/instruct-pix2pix: Syntology's graph links these samples to COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs (arXiv:2309.14356; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method.

Syntology 20 code samples harvested from 4 repositories linked to this paper: 17 ran (of which 2 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 5 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 20 samples from 4 repositories, 17 ran (12 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 17 samples that ran have no recorded date.

timothybrooks/instruct-pix2pix officialmentioned on GitHubpytorchNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs (arXiv:2309.14356; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
lsl001006/zone mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
mahdip72/InstructPix2Pix mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
mv-lab/InstructIR mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
huggingface/diffusers jaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RefDecoder: Enhancing Visual Generation with Conditional Video Decoding (arXiv:2605.15196; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
xuduo35/InstructPix2Pix pytorchMITSyntology: 14 samples, 14 ran (4 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

20 samples harvested: 17 ran (of which 2 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 5 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
5ran · violated contract
5ran · our draft was wrong
5ran
3unverified

Licence: 4 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

lsl001006/zone community (archive-listed) 2 samples, 0 ran · 2 unverified
register_attention_control in 9 papers null_text_w_ptp.py unverified Apache-2.0 (permissive) · 48d7b99aa07d02fe · report
text2image_instructpix2pix null_text_w_ptp.py unverified Apache-2.0 (permissive) · 70183cfe0ed40ffb · report
mahdip72/InstructPix2Pix community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
adapt_unet_for_pix2pix instruct_pix2pix/model.py ran · our draft was wrong MIT (permissive) · 569fbf037c75f18b · report fixture: signature unet:callable/0/? · returned MockUNet · level recorded 2026-09-22
mv-lab/InstructIR community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
InstructIR models/instructir.py ran · metamorphic tier: deterministic MIT (permissive) · da8184593ecc419a · report fixture: returned InstructIR · level recorded 2026-09-22
NAFBlock in 5 papers models/instructir.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 359c5485e870e3e6 · report fixture: returned NAFBlock · level recorded 2026-09-22
ICB models/instructir.py unverified MIT (permissive) · 4a0143b046f97246 · report
xuduo35/InstructPix2Pix community (archive-listed) 14 samples, 14 ran (4 instrument-failed) · 0 unverified
always in 65 papers ldm/modules/x_transformer.py ran · our draft was wrong MIT (permissive) · fe5dd5258046898c · report fixture: signature val:int/0/int · returned function · level recorded 2026-09-22
center_crop in 48 papers stable_txt2img.py ran fingerprinted MIT (permissive) · 81aae1af1d3e0807 · report fixture: signature img:ndarray/2/float · returned ndarray · level recorded 2026-09-25
chunk in 52 papers stable_txt2img.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 8241c0562bc710fd · report fixture: signature it:list/1/int, size:int/0/int · returned callable_iterator · level recorded, date not recorded
default in 430 papers ldm/modules/attention.py ran · violated contract MIT (permissive) · 424012cb37b31172 · report fixture: signature val:NoneType/0/?, d:callable/0/? · returned int · level recorded 2026-09-22
disabled_train in 172 papers ldm/models/diffusion/classifier.py ran · violated contract MIT (permissive) · 4cb732f513d69dfd · report fixture: signature self:callable/0/?, mode:bool/0/bool · returned SimpleModel · level recorded, date not recorded
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
ldm/modules/attention.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · aa5486a3650902d8 · report fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded
get_bert_token_for_string in 14 papers ldm/modules/embedding_manager.py ran · honoured contract MIT (permissive) · d5726f9e3a5684c3 · report fixture: signature tokenizer:callable/0/?, string:str/0/str · returned Tensor · level recorded 2026-09-22
get_clip_token_for_string in 16 papers ldm/modules/embedding_manager.py ran · honoured contract MIT (permissive) · 41c6eb3a0aa3eb46 · report fixture: signature tokenizer:callable/0/?, string:str/0/str · returned Tensor · level recorded 2026-09-22
get_embedding_for_clip_token in 13 papers ldm/modules/embedding_manager.py ran · our draft was wrong MIT (permissive) · 71c2df28a1008d03 · report fixture: signature embedder:callable/0/?, token:Tensor/1/float · returned Tensor · level recorded 2026-09-22
isimage in 65 papers ldm/util.py ran · violated contract fingerprinted MIT (permissive) · b1368330cf0f5642 · report fixture: signature x:Tensor/4/float · returned bool · level recorded 2026-09-24
ismap in 70 papers ldm/util.py ran · violated contract fingerprinted MIT (permissive) · d72762b700feee6f · report fixture: signature x:Tensor/4/float · returned bool · level recorded 2026-09-24
log_txt_as_img in 72 papers ldm/util.py ran MIT (permissive) here; the stored copy is pointer only · f41710299c49d36d · report fixture: signature wh:tuple/1/int, xc:list/1/str, size:int/0/int · returned Tensor · level recorded 2026-09-24
prune_checkpoint ldm/pruner.py ran MIT (permissive) · 9aee358ca7c31dbc · report fixture: signature old_state:dict/0/? · returned dict · level recorded 2026-09-25
uniq in 117 papers ldm/modules/attention.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 9a299fe5ae09e407 · report fixture: signature arr:list/1/int · returned dict_keys · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

3 sibling assemblies for InstructPix2Pix (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for InstructPix2Pix (graph method: InstructPix2Pix). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. text2image_instructpix2pix entry · level 0 · unverified · 70183cfe0ed40ffb
  2. register_attention_control helper · level 0 · unverified · 48d7b99aa07d02fe

harvested Assembly for InstructPix2Pix (graph method: InstructPix2Pix). 6 bricks; individually on a fixture: 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. InstructIR entry · level 1 · ran · da8184593ecc419a
  2. ICB model · level 0 · unverified · 4a0143b046f97246
  3. NAFBlock helper · level 1 · ran · 359c5485e870e3e6
  4. LayerNorm2d helper · level 1 · ran · 26e0e3b2df966dee
  5. SimpleGate helper · level 1 · ran · 488d68589ba5c45e
  6. LayerNormFunction helper · level 1 · ran · e0c7c3f6540a28db

harvested Assembly for InstructPix2Pix (graph method: InstructPix2Pix). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. adapt_unet_for_pix2pix entry · level 1 · ran · our draft was wrong · 569fbf037c75f18b

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2211.09800") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image EditingLanguage ModelingLanguage ModellingText to Image GenerationText-based Image Editing

Datasets

Introduced by this paper, per the archive.

InstructPix2Pix Image Editing Dataset

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Editing ImgEdit-Data Instruct-Pix2Pix Action 1.46 #8 of 9 Archive leaderboard report
Image Editing ImgEdit-Data Instruct-Pix2Pix Add 2.45 #8 of 9 Archive leaderboard report
Image Editing ImgEdit-Data Instruct-Pix2Pix Adjust 1.83 #8 of 9 Archive leaderboard report
Image Editing ImgEdit-Data Instruct-Pix2Pix Background 1.44 #8 of 9 Archive leaderboard report
Image Editing ImgEdit-Data Instruct-Pix2Pix Extract 1.44 #8 of 9 Archive leaderboard report
Image Editing ImgEdit-Data Instruct-Pix2Pix Hybrid 1.2 #8 of 9 Archive leaderboard report
Image Editing ImgEdit-Data Instruct-Pix2Pix Overall 1.88 #8 of 9 Archive leaderboard report
Image Editing ImgEdit-Data Instruct-Pix2Pix Remove 1.50 #8 of 9 Archive leaderboard report
Image Editing ImgEdit-Data Instruct-Pix2Pix Replace 2.01 #8 of 9 Archive leaderboard report
Image Editing ImgEdit-Data Instruct-Pix2Pix Style 3.55 #8 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections